Skip to content
supermemory-new
Get started
API Reference
Documents

Batch add documents

documents.batch_add(DocumentBatchAddParams**kwargs) -> DocumentBatchAddResponse
POST/v3/documents/batch

Add multiple documents in a single request. Each document can have any content type (text, url, file, etc.) and metadata

ParametersExpand Collapse
documents: Union[Iterable[DocumentsUnionMember0], Sequence[str]]
One of the following:
Iterable[DocumentsUnionMember0]
content: str

The content to extract and process into a document. This can be a URL to a website, a PDF, an image, or a video.

Plaintext: Any plaintext format

URL: A URL to a website, PDF, image, or video

We automatically detect the content type from the url’s response format.

container_tag: Optional[str]

Optional tag this document should be containerized by. This can be an ID for your user, a project ID, or any other identifier you wish to use to group documents.

maxLength100
Deprecatedcontainer_tags: Optional[Sequence[str]]

(DEPRECATED: Use containerTag instead) Optional tags this document should be containerized by. This can be an ID for your user, a project ID, or any other identifier you wish to use to group documents.

custom_id: Optional[str]

Optional custom ID of the document. This could be an ID from your database that will uniquely identify this document.

entity_context: Optional[str]

Optional entity context for this container tag. Max 1500 characters. Used during document processing to guide memory extraction.

maxLength1500
filepath: Optional[str]

Optional file path for the document (e.g., ‘/documents/reports/file.pdf’). Used by supermemoryfs to map documents to filesystem paths.

filter_by_metadata: Optional[Dict[str, Union[str, float, bool, Sequence[str]]]]

Optional metadata filter scoping which existing memories are pulled as context during ingestion. Scalar values match exactly (AND across keys); array values match ANY (OR within key). Only memories whose source documents match this filter are used as context.

One of the following:
str
float
bool
Sequence[str]
metadata: Optional[Dict[str, Union[str, float, bool, Sequence[str]]]]

Optional metadata for the document. This is used to store additional information about the document. You can use this to store any additional information you need about the document. Metadata can be filtered through. Keys must be strings and are case sensitive. Values can be strings, numbers, or booleans. You cannot nest objects.

One of the following:
str
float
bool
Sequence[str]
task_type: Optional[Literal["memory", "superrag"]]

Task type: “memory” (default) for full context layer with SuperRAG built in, “superrag” for managed RAG as a service.

One of the following:
"memory"
"superrag"
Sequence[str]
container_tag: Optional[str]

Optional tag this document should be containerized by. This can be an ID for your user, a project ID, or any other identifier you wish to use to group documents.

maxLength100
Deprecatedcontainer_tags: Optional[Sequence[str]]

(DEPRECATED: Use containerTag instead) Optional tags this document should be containerized by. This can be an ID for your user, a project ID, or any other identifier you wish to use to group documents.

content: Optional[None]
entity_context: Optional[str]

Optional entity context for this container tag. Max 1500 characters. Used during document processing to guide memory extraction.

maxLength1500
filepath: Optional[str]

Optional file path for the document (e.g., ‘/documents/reports/file.pdf’). Used by supermemoryfs to map documents to filesystem paths.

filter_by_metadata: Optional[Dict[str, Union[str, float, bool, Sequence[str]]]]

Optional metadata filter scoping which existing memories are pulled as context during ingestion. Scalar values match exactly (AND across keys); array values match ANY (OR within key). Only memories whose source documents match this filter are used as context.

One of the following:
str
float
bool
Sequence[str]
metadata: Optional[Dict[str, Union[str, float, bool, Sequence[str]]]]

Optional metadata for the document. This is used to store additional information about the document. You can use this to store any additional information you need about the document. Metadata can be filtered through. Keys must be strings and are case sensitive. Values can be strings, numbers, or booleans. You cannot nest objects.

One of the following:
str
float
bool
Sequence[str]
task_type: Optional[Literal["memory", "superrag"]]

Task type: “memory” (default) for full context layer with SuperRAG built in, “superrag” for managed RAG as a service.

One of the following:
"memory"
"superrag"
ReturnsExpand Collapse
class DocumentBatchAddResponse: …
failed: float

Count of documents that failed to add

results: List[Result]

Array of results for each document in the batch

id: str

Unique identifier of the document (empty string for failed items)

status: str

Status of the document (e.g. ‘done’, ‘queued’, ‘error’)

details: Optional[str]

Additional error details when status is ‘error’

error: Optional[str]

Error message when status is ‘error’

success: float

Count of documents successfully added

Batch add documents

import os
from supermemory import Supermemory

client = Supermemory(
    api_key=os.environ.get("SUPERMEMORY_API_KEY"),  # This is the default and can be omitted
)
response = client.documents.batch_add(
    documents=[{
        "content": "Our API rate limits are 100 req/min on free and 1000 on pro. Clients should use exponential backoff on 429s."
    }],
)
print(response.failed)
{
  "failed": 0,
  "results": [
    {
      "id": "id",
      "status": "status",
      "details": "details",
      "error": "error"
    }
  ],
  "success": 0
}
Returns Examples
{
  "failed": 0,
  "results": [
    {
      "id": "id",
      "status": "status",
      "details": "details",
      "error": "error"
    }
  ],
  "success": 0
}